Multi-Objective Balanced Optimization Task Offloading Algorithm Based on Multi-Agent Collaboration

With the development of the Internet of Things and multi-access edge computing, latency-sensitive tasks impose higher requirements on network computing capability and service quality. Existing task offloading methods usually focus on a single performance metric and often adopt time-slot-driven decision mechanisms, which may introduce additional waiting latency and increase system cost. To address these problems, this paper proposes a task-driven offloading algorithm based on Balanced Multi-Agent Deep Deterministic Policy Gradient (BMADDPG). First, a four-layer integrated air–space–ground multi-access edge computing network model is constructed, consisting of ground devices, unmanned aerial vehicles (UAVs), low-Earth-orbit (LEO) satellites, and cloud servers. Multi-level computing node collaboration is used to improve the system computing capability. Second, the task offloading process is modeled as a multi-agent Markov decision process, where ground user devices act as agents. A centralized Critic and distributed Actor structure is adopted for collaborative decision-making. The proposed algorithm uses DDPG to handle continuous action spaces and triggers offloading decisions immediately upon task arrival, thereby avoiding time-slot waiting overhead. Meanwhile, latency, energy consumption, and load balancing constraints are incorporated into the reward function to guide global resource allocation. Simulation results show that BMADDPG converges stably within about 800 training episodes. Compared with DDPG, DQN, PPO, and D3QN, it reduces average task processing latency by approximately 22.67% and decreases total system cost by at least 18.32% under high-load scenarios.